CN111594335B

CN111594335B - Catalyst warm-up monitoring device, system, and method for internal combustion engine

Info

Publication number: CN111594335B
Application number: CN202010099427.7A
Authority: CN
Inventors: 武藤晴文; 片山章弘; 池尻祐贵; 桥本洋介
Original assignee: Toyota Motor Corp
Current assignee: Toyota Motor Corp
Priority date: 2019-02-20
Filing date: 2020-02-18
Publication date: 2022-06-24
Anticipated expiration: 2040-02-18
Also published as: JP2020133513A; US20200263592A1; JP6593561B1; DE102020103441A1; CN111594335A; US11143083B2; DE102020103441B4

Abstract

Provided are a catalyst warm-up monitoring device, a catalyst warm-up monitoring system, a catalyst warm-up monitoring method, a data analysis device, an internal combustion engine control device, and a reception device for an internal combustion engine. The storage device stores the mapping data and the corresponding association data. The map data specifies a map that takes as input the previous value of the estimated value of the temperature of the catalyst and the warm-up operation amount variable, and outputs the estimated value of the temperature of the catalyst. The correspondence correlation data correlates an integrated value of an intake air amount of the internal combustion engine from the start of the internal combustion engine and a temperature of the catalyst. The execution device repeatedly calculates an estimated value of the temperature of the catalyst based on the output of the map. When the correspondence relationship between the accumulated value and the estimated value is different from the correspondence relationship between the accumulated value and the temperature of the catalyst in the correspondence relation data, it is determined that the preheating process is abnormal.

Description

Catalyst warm-up monitoring device, system, and method for internal combustion engine

Technical Field

The present disclosure relates to a catalyst warm-up monitoring device for an internal combustion engine, a catalyst warm-up monitoring system for an internal combustion engine, a data analysis device, a control device for an internal combustion engine, and a reception device.

Background

For example, japanese patent application laid-open No. 2007-32316 describes a device that performs a catalyst warm-up process by retarding an ignition timing. In this apparatus, the end condition of the preheating process is set based on a detection value of an oxygen sensor provided downstream of the catalyst, a temperature of cooling water of the internal combustion engine, and the like.

Even if a control logic for executing the warm-up process is mounted on the control device, the catalyst cannot be warmed up for an assumed period of time when some abnormality occurs in the control logic or the like. In fact, it may be impossible to cope with the case where the exhaust characteristic after the cold start of the internal combustion engine is lower than the assumed exhaust characteristic.

Disclosure of Invention

Examples of the present disclosure are described below.

Example 1. a catalyst warm-up monitoring device for an internal combustion engine, comprising an actuator and a storage device, wherein the catalyst warm-up monitoring device is applied to an internal combustion engine provided with a catalyst in an exhaust passage, the storage device is configured to store map data and correspondence data, the map data specifying a map in which the last value of the estimated value of the temperature of the catalyst and the warm-up operation amount variable are input and the estimated value of the temperature of the catalyst is output, the warm-up operation amount variable is a variable relating to an operation amount of an operation portion of the internal combustion engine and an operation portion used in the warm-up process of the catalyst, the correspondence relation data associates an integrated value of an intake air amount of the internal combustion engine from a start of the internal combustion engine and a temperature of the catalyst with each other, and the execution device executes: the preheating treatment is carried out; accumulation processing for calculating the accumulation value; an acquisition process of acquiring a last value of the estimated values of the warm-up operation amount variable and the temperature of the catalyst; a temperature calculation process of repeatedly calculating an estimated value of the temperature of the catalyst based on an output of the map with the warm-up operation amount variable and the previous value acquired by the acquisition process as inputs to the map; a determination process of determining that the preheating process is abnormal when a correspondence relationship between the integrated value and the estimated value is different from a correspondence relationship between the integrated value and the temperature of the catalyst in the correspondence relation data; and a handling process of handling the abnormality by operating predetermined hardware when a determination is made that the abnormality is present.

The accumulated value has a correlation with the total amount of combustion energy in the internal combustion engine. Therefore, the temperature of the catalyst can be grasped by integrating the values. Further, since the warm-up control of the catalyst is determined by the warm-up manipulated variable, the temperature of the catalyst can be grasped by the warm-up manipulated variable. For this reason, in the above configuration, when the estimated value of the catalyst temperature calculated based on the warm-up operation amount variable does not match the correspondence relationship data in which the integrated value and the temperature of the catalyst are correlated with each other, it is determined that the warm-up process is abnormal. Therefore, when an abnormality occurs in the warm-up process, it is possible to detect that the exhaust characteristic after the cold start of the internal combustion engine is lower than the assumed exhaust characteristic, and further, it is possible to cope with this situation when the exhaust characteristic after the cold start of the internal combustion engine is lower than the assumed exhaust characteristic.

Example 2 the catalyst warm-up monitoring device for an internal combustion engine according to example 1, wherein the internal combustion engine includes a valve characteristic varying device that varies a valve characteristic of an intake valve, wherein the input of the map includes a valve characteristic variable that is a variable related to the valve characteristic, wherein the acquiring process includes a process of acquiring the valve characteristic variable, and wherein the temperature calculating process calculates the estimated value based on an output of the map that includes the input to the map and the valve characteristic variable.

The combustion temperature of the air-fuel mixture in the combustion chamber changes according to the valve characteristic variable, and the temperature of the exhaust gas discharged to the exhaust passage changes. Therefore, according to the above configuration, the estimated value of the temperature of the catalyst can be calculated with higher accuracy by setting the valve characteristic variable as an input to the map.

Example 3 according to the catalyst warm-up process monitoring apparatus for an internal combustion engine described in the above example 1 or 2, the warm-up operation amount includes an ignition variable that is a variable relating to ignition timing.

In the above configuration, the ignition timing is operated to increase the temperature of the exhaust gas, thereby warming up the catalyst. In the above configuration, the degree of temperature increase of the exhaust gas by the operation of the ignition timing can be grasped by the ignition variable, and the estimated value of the temperature of the catalyst can be calculated.

Example 4 the catalyst warm-up monitoring device for an internal combustion engine according to example 3, wherein the map includes an injection amount variable as a variable relating to an injection amount of fuel, the acquiring includes acquiring the injection amount variable, and the temperature calculating includes calculating the estimated value based on an output of the map including the input to the map and the injection amount variable.

In cold start of the internal combustion engine or the like, the actual injection amount tends to increase with respect to the fuel amount at the target air-fuel ratio when the air-fuel ratio is normal, for the purpose of avoiding misfire or the like. In this case, not only is the actual air-fuel ratio richer than the target air-fuel ratio in the normal state, but the degree of the richness is not constant. Therefore, the combustion temperature may change compared to the case where a predetermined air-fuel ratio is assumed, and further, the temperature of the catalyst may change. Thus, in the above configuration, the injection amount variation is included in the input of the map. Thus, even when the amount of fuel is increased, the temperature of the catalyst can be estimated by reflecting the influence of the increase.

Example 5. according to the catalyst warm-up monitoring apparatus for an internal combustion engine described in any one of examples 1 to 4 above, the warm-up process includes a dither control process of operating a fuel injection valve as the operation portion in order to make a part of cylinders of a plurality of cylinders of the internal combustion engine rich and make a cylinder other than the part of cylinders of the plurality of cylinders lean, an air-fuel ratio richer than a stoichiometric air-fuel ratio in the rich-burn cylinder, an air-fuel ratio leaner than the stoichiometric air-fuel ratio in the lean-burn cylinder, the warm-up operation amount set as an input to the map including an amplitude value variable, the amplitude value variable is a variable relating to a degree of richness of the air-fuel ratio of the rich-burn cylinder with respect to a theoretical air-fuel ratio and a degree of leanness of the air-fuel ratio of the lean-burn cylinder with respect to the theoretical air-fuel ratio.

In the above configuration, the catalyst can be warmed up by an oxidation reaction of oxygen discharged from the lean-burn cylinder and fuel discharged from the rich-burn cylinder. At this time, the temperature of the catalyst increases depending on the difference between the air-fuel ratio of the rich-burn cylinder and the air-fuel ratio of the lean-burn cylinder. In the above configuration, the temperature of the catalyst can be calculated with high accuracy by setting the amplitude value variable as the warm-up manipulated variable and setting the amplitude value variable as the input to the map.

Example 6 the catalyst warm-up process monitoring device for an internal combustion engine according to any one of examples 1 to 5, wherein the internal combustion engine includes a port injection valve that injects fuel into an intake passage and an in-cylinder injection valve that injects fuel into a combustion chamber of the internal combustion engine, and wherein an input of the map includes an injection distribution variable that is a variable relating to an injection distribution ratio of an amount of fuel injected by the port injection valve to a sum of an injection amount of fuel from the port injection valve and an injection amount of fuel from the in-cylinder injection valve, and wherein the acquiring process includes a process of acquiring the injection distribution variable, and wherein the temperature calculating process is a process of calculating the estimated value based on an output of the map that further includes the injection distribution variable as an input to the map.

In the above configuration, the injection distribution variable is included in the input to the map. Thereby, an estimated value reflecting the difference in combustion between the case where fuel is injected from the port injection valve and the case where fuel is injected from the in-cylinder injection valve can be calculated.

Example 7 the catalyst warm-up monitoring apparatus for an internal combustion engine according to any one of the above examples 1 to 6, the internal combustion engine including: an EGR passage configured to allow a fluid flowing into the exhaust passage from a combustion chamber of the internal combustion engine to flow into an intake passage; and an EGR valve configured to adjust a flow path cross-sectional area of the EGR passage, wherein an EGR variable that is a variable indicating an EGR rate, which is a ratio of a flow rate of the fluid flowing into the intake passage through the EGR passage to a sum of the flow rate of the air taken into the intake passage and the flow rate of the fluid flowing into the intake passage through the EGR passage, is included in an input of the map, wherein the acquiring process includes a process of acquiring the EGR variable, and the temperature calculating process is a process of calculating the estimated value based on an output of the map in which the input to the map further includes the EGR variable.

In the above configuration, the input to the map is made to include an EGR variable. This makes it possible to calculate an estimated value reflecting a difference in temperature of the exhaust gas discharged to the exhaust passage due to a difference in combustion when the EGR rate is different.

Example 8 the catalyst warm-up process monitoring device for an internal combustion engine according to any one of examples 1 to 7, wherein an atmospheric pressure variable that is a variable related to atmospheric pressure is included in an input of the map, the acquiring process includes a process of acquiring the atmospheric pressure variable, and the temperature calculating process is a process of calculating the estimated value based on an output of the map that further includes the atmospheric pressure variable in the input to the map.

In the above configuration, the input to the map is made to include an atmospheric pressure variable. This makes it possible to calculate an estimated value reflecting combustion differences according to the atmospheric pressure.

Example 9 the catalyst warm-up process monitoring device for an internal combustion engine according to any one of examples 1 to 8, wherein a liquid whose flow rate is adjusted by an adjusting device flows through the internal combustion engine, and wherein the map input includes a flow rate variable that is a variable related to the flow rate of the liquid, and wherein the acquiring includes acquiring the flow rate variable, and wherein the temperature calculating includes calculating the estimated value based on an output of the map that includes the flow rate variable in addition to the input to the map.

In the above configuration, the input to the map is made to include a flow rate variable. This makes it possible to calculate an estimated value reflecting a temperature change of each part of the internal combustion engine due to heat exchange between the liquid and the internal combustion engine.

Example 10 according to the catalyst warm-up monitoring device for an internal combustion engine described in any one of examples 1 to 9, the catalyst is divided into N partial regions arranged in parallel in a flow direction of the fluid flowing into the catalyst, the N partial regions being set as a1 st partial region to an N th partial region in order from an upstream side of the catalyst, the obtaining includes a process of obtaining a previous value of an estimated value of a temperature of each of the 1 st partial region to the N th partial region as a previous value of the estimated value, the map includes a1 st map and an i-th map as maps outputting the estimated value of the temperature of the 1 st partial region, the 1 st map is inputted with at least a variable other than the estimated value of the temperature of the partial region located at least downstream of the 1 st partial region among variables obtained by the obtaining process, i is an integer of 2 or more and N or less, the ith map is a map that outputs an estimated value of the temperature of the ith sub-region, and the temperature calculation process includes a process of calculating estimated values of the temperatures of the 1 st to nth sub-regions by using, as inputs, at least an estimated value of the temperature of the i-1 th sub-region and a previous value of the estimated value of the temperature of the ith sub-region, the processes including: a process of calculating an estimated value of the temperature of the 1 st partial region by inputting to the 1 st map at least variables other than the estimated value of the temperature at least downstream of the 1 st partial region among the variables acquired by the acquisition process; and a process of calculating an estimated value of the temperature of the i-th partial region by setting at least the estimated value of the temperature of the i-th partial region-1 and a last value of the estimated value of the temperature of the i-th partial region as inputs of the i-th map.

In the above configuration, the temperature of the i-th partial region is estimated based on the estimated value of the temperature of the i-1-th partial region. Thus, the temperature of the i-th partial region can be estimated in consideration of heat exchange between the i-th partial region and the i-1 st partial region. Therefore, the heat exchange between the partial regions of the catalyst can be reflected more easily than in the case where the map for calculating the temperature of the single catalyst is formed by using the single map, for example. Therefore, the structure of each map can be simplified, and the accuracy of estimating the temperature can be improved.

Example 11 is the catalyst warm-up process monitoring device of an internal combustion engine according to any one of examples 1 to 9, wherein the map includes a steady map that has the warm-up manipulated variable as an input and outputs a steady temperature that is a value at which the temperature of the catalyst converges when the internal combustion engine is in steady operation, and a time constant map that has an air quantity variable that is a variable related to an intake air quantity of the internal combustion engine, a time constant variable that determines a time constant for converging the current temperature to the steady temperature as an input, and outputs the time constant variable, the temperature calculating process including: a steady state calculation process of calculating an estimated value of the steady state temperature based on an output of the steady map with the warm-up manipulated variable as an input; a time constant calculation process of calculating the time constant variable based on an output of the time constant map with the previous value of the air volume variable, the stable temperature, and the estimated value as an input; and a process of calculating an estimated value of the temperature of the catalyst by bringing the estimated value toward the stable temperature based on the time constant variable calculated by the time constant calculation process.

In the above configuration, transient behavior of the temperature of the catalyst can be estimated by the temperature in the steady state and the time constant variable.

Example 12 the catalyst warm-up monitoring apparatus for an internal combustion engine according to any one of examples 1 to 11, wherein the countermeasure processing includes notification processing for notifying that the warm-up processing is abnormal by operating a notification device that is the predetermined hardware.

In the above configuration, it is possible to urge the handling of the abnormality in the preheating process by the notification process.

An example 13 is a catalyst warm-up monitoring system for an internal combustion engine, including the actuator and the storage device described in any one of examples 1 to 12, wherein the actuator includes a1 st actuator and a2 nd actuator, and the 1 st actuator is mounted on a vehicle and configured to execute: the acquisition process; a vehicle-side transmission process of transmitting the data acquired by the acquisition process to the outside of the vehicle; a vehicle-side reception process of receiving a signal based on the estimated value calculated by the temperature calculation process; and the handling processing, wherein the 2 nd execution device is disposed outside the vehicle, and is configured to execute: an external-side reception process of receiving data transmitted by the vehicle-side transmission process; the temperature calculation process; and an external transmission process of transmitting a signal based on the estimated value calculated by the temperature calculation process to the vehicle.

In the above configuration, the temperature calculation process is executed outside the vehicle, so that the calculation load of the in-vehicle device can be reduced.

Example 14 is a data analysis device including the 2 nd execution device and the storage device described in example 13.

Example 15 a control device for an internal combustion engine, including the 1 st actuator described in example 13 above.

Example 16 a reception device, which is hardware constituting a part of the catalyst warm-up monitoring system according to example 13, is configured to execute the vehicle-side reception process.

Example 17 is embodied as a method for monitoring a catalyst warm-up process of an internal combustion engine, which executes the various processes described in any one of examples 1 to 16.

Example 18 is embodied as a non-transitory computer-readable recording medium storing a program for causing a processing device to execute the various processes described in any one of examples 1 to 16.

Drawings

Fig. 1 is a diagram showing the configuration of a control device and a vehicle drive system according to embodiment 1.

Fig. 2 is a block diagram showing a part of the processing executed by the control device of the embodiment.

Fig. 3 is a flowchart showing the procedure of the catalyst temperature estimation process according to this embodiment.

Fig. 4 is a view showing a partial region of the catalyst of this embodiment.

Fig. 5 is a flowchart showing the procedure of the catalyst warm-up monitoring process of this embodiment.

Fig. 6 is a diagram showing a system for generating mapping data according to this embodiment.

Fig. 7 is a flowchart showing the steps of the learning process of the map data according to this embodiment.

Fig. 8 is a block diagram showing a part of the processing executed by the control device of embodiment 2.

Fig. 9 is a flowchart showing the procedure of the catalyst temperature estimation process according to this embodiment.

Fig. 10 is a flowchart showing the procedure of the catalyst temperature estimation process according to embodiment 3.

Fig. 11 is a flowchart showing the procedure of the catalyst temperature estimating process of embodiment 4.

Fig. 12 is a diagram showing the configuration of the catalyst temperature estimation system according to embodiment 5.

Parts (a) and (b) of fig. 13 are flowcharts showing steps of processing executed by the catalyst temperature estimation system of fig. 12.

Detailed Description

< embodiment 1 >

Hereinafter, a first embodiment of a catalyst warm-up monitoring device 1 for an internal combustion engine will be described with reference to fig. 1 to 7.

An intake passage 12 of the internal combustion engine 10 shown in fig. 1 is provided with a throttle valve 14 and a port injection valve 16 in this order from the upstream side. The air taken into the intake passage 12 and the fuel injected from the port injection valve 16 flow into a combustion chamber 24 partitioned by the cylinder 20 and the piston 22 as the intake valve 18 opens. The in-cylinder injection valve 26 is capable of injecting fuel into the combustion chamber 24. In the combustion chamber 24, a mixture of fuel and air is used for combustion by spark discharge of the ignition device 28. The combustion energy generated by the combustion is converted into rotational energy of the crankshaft 30 via the piston 22. The air-fuel mixture used for combustion is discharged as exhaust gas to the exhaust passage 34 as the exhaust valve 32 is opened. A catalyst 36 such as a three-way catalyst having an oxygen storage capacity is provided in the exhaust passage 34.

The rotational power of the crankshaft 30 is transmitted to an intake camshaft 40 and an exhaust camshaft 42 via a timing chain 38. In the present embodiment, the power of the timing chain 38 is transmitted to the intake camshaft 40 via the variable valve timing device 44. The variable valve timing device 44 is an actuator that adjusts the opening timing of the intake valve 18 by adjusting the rotational phase difference between the crankshaft 30 and the intake camshaft 40.

Further, a portion downstream of the throttle valve 14 in the intake passage 12 is connected to the exhaust passage 34 via an EGR passage 46. The EGR passage 46 is provided with an EGR valve 48 for adjusting the cross-sectional area of the flow passage.

The coolant in the internal combustion engine 10 flows into a temperature control device 54 such as a heater or a device for adjusting the temperature of the hydraulic oil in the transmission 62 through a coolant circulation path 52 by the power of the pump 50, exchanges heat, and then flows into the internal combustion engine 10 again. The circulation amount of the cooling water in the cooling water circulation path 52 is adjusted by a flow rate control valve 56 that adjusts the cross-sectional area of the flow path of the cooling water circulation path 52.

Further, a drive wheel 64 is mechanically connected to the crankshaft 30 via a torque converter 60 and a transmission 62.

The control device 70 controls the internal combustion engine 10, and operates operation portions of the internal combustion engine 10 such as the throttle valve 14, the port injection valve 16, the in-cylinder injection valve 26, the ignition device 28, the variable valve timing device 44, the EGR valve 48, and the flow rate control valve 56 in order to control the torque, the exhaust gas component ratio, and the like as controlled amounts thereof. Fig. 1 shows operation signals MS1 to MS7 of throttle valve 14, port injection valve 16, in-cylinder injection valve 26, ignition device 28, variable valve timing device 44, EGR valve 48, and flow control valve 56, respectively.

The control device 70 refers to the intake air amount Ga detected by the airflow meter 80, the output signal Scr of the crank angle sensor 82, the output signal Sca of the intake cam angle sensor 84, and the air-fuel ratio Af detected by the air-fuel ratio sensor 86 provided upstream of the catalyst 36 during control of the control amount. The controller 70 refers to the temperature of the cooling water (water temperature THW) of the internal combustion engine 10 detected by the water temperature sensor 88 and the atmospheric pressure Pa detected by the atmospheric pressure sensor 90.

The control device 70 includes a CPU72, a ROM74, a storage device 76 as an electrically rewritable nonvolatile memory, and a peripheral circuit 77, and can communicate with each other through the local network 78. The peripheral circuit 77 includes a circuit that generates a clock signal that defines an internal operation, a power supply circuit, a reset circuit, and the like.

The control device 70 executes the control of the above-described control amount by the CPU72 executing a program stored in the ROM 74.

Fig. 2 shows a part of processing realized by the CPU72 executing a program stored in the ROM 74.

The intake phase difference calculation process M10 is a process of calculating an intake phase difference DIN, which is the phase difference between the rotation angle of the intake camshaft 40 with respect to the rotation angle of the crankshaft 30, based on the output signal Scr of the crank angle sensor 82 and the output signal Sca of the intake side cam angle sensor 84. The target intake air phase difference calculation process M12 is basically a process of variably setting the target intake air phase difference DIN based on the operating point of the internal combustion engine 10. In the present embodiment, the operating point is defined by the rotation speed NE and the inflation efficiency η. Here, the CPU72 calculates the rotation speed NE based on the output signal Scr of the crank angle sensor 82, and calculates the inflation efficiency η based on the rotation speed NE and the intake air amount Ga. The charging efficiency η is a parameter for determining the amount of air to be charged into the combustion chamber 24. The intake air phase difference calculation process M10 includes a process of changing the actual target intake air phase difference DIN with respect to the target intake air phase difference DIN corresponding to the operating point when the water temperature THW does not satisfy the specific temperature.

The intake phase difference control process M14 is a process of outputting an operation signal MS5 to the variable valve timing device 44 to operate the variable valve timing device 44 in order to control the intake phase difference DIN to the target intake phase difference DIN.

The base injection amount calculation process M20 is a process of calculating the base injection amount Qb based on the inflation efficiency η. The basic injection amount Qb is a basic value of the amount of fuel for making the air-fuel ratio of the air-fuel mixture in the combustion chamber 24 the target air-fuel ratio. More specifically, when the inflation efficiency η is expressed by a percentage, for example, the base injection amount calculation process M20 may be a process of calculating the base injection amount Qb by multiplying the inflation efficiency η by the fuel amount QTH per 1% of the inflation efficiency η for setting the air-fuel ratio to the target air-fuel ratio. The base injection amount Qb is an amount of fuel calculated to control the air-fuel ratio to the target air-fuel ratio based on the amount of air filled into the combustion chamber 24. In the present embodiment, a theoretical air-fuel ratio is exemplified as the target air-fuel ratio.

The feedback process M22 is a process of calculating and outputting a feedback correction coefficient KAF obtained by adding "1" to the correction ratio δ of the base injection amount Qb. The correction ratio δ of the base injection amount Qb is a feedback manipulated variable that is a manipulated variable for feedback-controlling the air-fuel ratio Af to a target value Af. Specifically, the feedback process M22 sets the correction ratio δ to the sum of the output values of the proportional element and the derivative element, which are input as the difference between the air-fuel ratio Af and the target value Af, and the output value of the integral element, which is held and output as the integrated value of the value corresponding to the difference.

The low temperature correction process M24 is a process of calculating the low temperature increase coefficient Kw to a value larger than "1" in order to increase the base injection amount Qb when the water temperature THW is lower than a predetermined temperature Tth (for example, 60 ℃). Specifically, the low temperature increase coefficient Kw is calculated to be a larger value when the water temperature THW is low than when it is high. When the water temperature THW is equal to or higher than the predetermined temperature Tth, the low temperature increase coefficient Kw is set to "1" so that the correction amount of the low temperature increase coefficient Kw with respect to the basic injection amount Qb becomes zero.

The start-time injection amount setting process M28 is a process of setting the start-time injection amount of the internal combustion engine 10. The start-time injection amount setting process M28 is a process of setting the injection amount so as to inject a large amount of fuel, which is necessary for making the air-fuel ratio of the air-fuel mixture to be burned in the combustion chamber 24 the stoichiometric air-fuel ratio, from the viewpoint of suppressing misfires in particular at the time of starting the internal combustion engine 10.

Injection valve operation process M30 is a process of outputting operation signal MS2 to port injection valve 16 for operating port injection valve 16 or operation signal MS3 to in-cylinder injection valve 26 for operating in-cylinder injection valve 26. Specifically, after the start of internal combustion engine 10, injection valve operation process M30 is a process of setting the injection ratio of port injection valve 16 to required injection quantity Qd to an injection distribution ratio Kp, and operating port injection valve 16 and in-cylinder injection valve 26 based on this injection distribution ratio Kp. Further, at the time of starting of the internal combustion engine 10, the injection valve operation process M30 is a process of operating the port injection valves 16 so that the fuel of the amount of fuel set by the start-time injection amount setting process M28 is injected by the port injection valves 16.

The EGR control process M40 is basically a process of operating the EGR valve 48 to control the EGR rate Regr based on the rotation speed NE and the charging efficiency η that define the operating point of the internal combustion engine 10. The EGR ratio is a ratio of the flow rate of the fluid flowing into the intake passage 12 through the EGR passage 46 to the sum of the flow rate of the air taken into the intake passage 12 and the flow rate of the fluid flowing into the intake passage 12 through the EGR passage 46. The EGR control process M40 includes a process of controlling the EGR rate Regr so as to be deviated from the EGR rate Regr determined according to the operating point when the water temperature THW is low.

The preheating treatment M42 is a treatment as follows: in cold start of the internal combustion engine 10, the ignition timing is retarded by a predetermined amount with respect to the base ignition timing in the normal state determined based on the rotation speed NE and the charging efficiency η, and thus the amount of heat that does not act on the torque in the combustion energy of the air-fuel mixture is increased. More specifically, the warm-up process M42 is a process of retarding the ignition timing by cold start when the water temperature THW at the time of start is equal to or lower than a predetermined temperature.

The CPU72 executes the process of monitoring whether the process of warming up the catalyst 36 is normally performed or not by the process shown in fig. 2 during the cold start of the internal combustion engine 10. This will be described in detail below.

Fig. 3 shows the steps of the estimation process of the temperature of the catalyst 36. The process shown in fig. 3 is realized by the CPU72 repeatedly executing a temperature estimation program 74a stored in the ROM74 shown in fig. 1, for example, at predetermined cycles in association with a cold start of the internal combustion engine 10. In the following, the step number of each process is expressed by a numeral denoted by "S" at the head.

In the series of processing shown in fig. 3, the CPU72 first acquires the rotation speed NE, the charging efficiency η, the ignition timing average value aigave, the intake air phase difference average value DINave, the water temperature THW, the previous value of the 1 st temperature Tcat1, the previous value of the 2 nd temperature Tcat2, and the previous value of the 3 rd temperature Tcat3 (S10). Here, the ignition timing average value aigave and the intake phase difference average value DINave are the average value of the ignition timing aig and the average value of the intake phase difference DIN in the processing cycle of S10, respectively. Note that the 1 st temperature Tcat1, the 2 nd temperature Tcat2, and the 3 rd temperature Tcat3 are temperatures of respective partial regions when the region from the upstream side to the downstream side in the catalyst 36 is divided into 3 partial regions and the 1 st partial region a1, the 2 nd partial region a2, and the 3 rd partial region A3 are set in this order from the upstream side as shown in fig. 4. The previous value is a value calculated at the previous execution of the series of processing shown in fig. 3.

Next, the CPU72 substitutes values of variables other than the 2 nd temperature Tcat2 and the 3 rd temperature Tcat3 among the variables acquired in the process of S10 into an input variable that outputs a map of the 1 st temperature Tcat1 (S12). That is, the CPU72 substitutes the rotation speed NE for the input variable x (1), the charge efficiency η for the input variable x (2), the ignition timing average value aigave for the input variable x (3), and the intake phase difference average value DINave for the input variable x (4). The CPU72 substitutes the water temperature THW for the input variable x (5) and substitutes the previous value of the 1 st temperature Tcat1 for the input variable x (6).

Next, the CPU72 calculates a1 st temperature Tcat1 by inputting the input variables x (1) to x (6) to a map that outputs a1 st temperature Tcat1 (S14). The map is composed of a neural network in which the number of intermediate layers is "α f", the activation functions h1 to h α f of the intermediate layers are hyperbolic tangent functions, and the activation function f of the output layer is ReLU. The ReLU is a function that outputs the smaller of the input value and zero.

For example, the value of each node in the 1 st intermediate layer is generated by inputting the output obtained when the input variables x (1) to x (6) are input to the activation function h1 in a linear map defined by coefficients wF (1) ji (j is 0 to nf1, i is 0 to 6). That is, when m is 1, 2, …, or α f, the value of each node in the mth intermediate level is generated by inputting the output of the linear map defined by the coefficient wf (m) to the activation function hm. Here, nf1, nf2, …, and nf α represent the number of nodes in the 1 st, 2 nd, … th, and α f th intermediate layers, respectively. Incidentally, wF (1) j0 and the like are bias parameters, and the input variable x (0) is defined as "1".

Next, the CPU72 generates input variables x (1) to x (7) that output the map of the 2 nd temperature Tcat2 (S16). Here, the input variables x (1) to x (5) are the same as the input variables x (1) to x (5) generated in the processing of S12. The CPU72 substitutes the last value of the 2 nd temperature Tcat2 for the input variable x (6), and substitutes the 1 st temperature average value Tcat1ave for the input variable x (7). The 1 st temperature average value Tcat1ave is an average value of a plurality of latest sample values of the 1 st temperature Tcat1 including the present value of the 1 st temperature Tcat1, i.e., the 1 st temperature Tcat1 calculated in the present process of S14.

Next, the CPU72 calculates a2 nd temperature Tcat2 by inputting the input variables x (1) to x (7) to a map that outputs a2 nd temperature Tcat2 (S18). The mapping is composed of a neural network in which the intermediate layers are "α s", the activation functions h1 to h α s of the intermediate layers are hyperbolic tangent functions, and the activation function f of the output layer is ReLU. For example, the value of each node in the 1 st intermediate layer is generated by inputting the output obtained when the input variables x (1) to x (7) are input to the activation function h1 in a linear map defined by coefficients wS (1) ji (j is 0 to ns1, i is 0 to 7). That is, when m is 1, 2, …, or α s, the value of each node in the mth intermediate level is generated by inputting the output of the linear map defined by the coefficient ws (m) to the activation function hm. Here, n1, n2, …, and n α s are the number of nodes in the 1 st, 2 nd, … th, and α s th intermediate layers, respectively. Incidentally, wS (1) j0 and the like are bias parameters, and the input variable x (0) is defined as "1".

Next, the CPU72 generates input variables x (1) to x (7) that output the map of the 3 rd temperature Tcat3 (S20). Here, the input variables x (1) to x (5) are the same as the input variables x (1) to x (5) generated in the processing of S12. The CPU72 substitutes the previous value of the 3 rd temperature Tcat3 for the input variable x (6) and substitutes the 2 nd temperature average value Tcat2ave for the input variable x (7). The 2 nd temperature average value tcave 2ave is an average value of a plurality of latest sample values of the 2 nd temperature Tcat2 including the present value of the 2 nd temperature Tcat2 which is the 2 nd temperature Tcat2 calculated in the present process of S18.

Next, the CPU72 calculates a3 rd temperature Tcat3 by inputting the input variables x (1) to x (7) to a map that outputs a3 rd temperature Tcat3 (S22). The map is composed of a neural network in which the number of intermediate layers is "α t", the activation functions h1 to h α t of the intermediate layers are hyperbolic tangent functions, and the activation function f of the output layer is ReLU. For example, the value of each node in the 1 st intermediate layer is generated by inputting the output when the input variables x (1) to x (7) are input to the activation function h1 in a linear map defined by coefficients wT (1) ji (j is 0 to nt1, i is 0 to 7). That is, when m is 1, 2, …, or α t, the value of each node in the mth intermediate level is generated by inputting the output of the linear map defined by the coefficient wt (m) to the activation function hm. Here, n1, n2, …, and n α t are the number of nodes in the 1 st, 2 nd, …, and α t th intermediate layers, respectively. Incidentally, wT (1) j0 and the like are bias parameters, and the input variable x (0) is defined as "1".

Next, the CPU72 substitutes the 2 nd temperature Tcat2 calculated this time in the processing of S18 into the catalyst temperature Tcat (S24), and once ends the series of processing. Incidentally, when the processing of fig. 3 is executed first, predetermined default values may be used as the previous value of the 1 st temperature Tcat1, the previous value of the 2 nd temperature Tcat2, and the previous value of the 3 rd temperature Tcat 3. Even when the default value is deviated from the actual temperature, the 1 st temperature Tcat1, the 2 nd temperature Tcat2, and the 3 rd temperature Tcat3 converge to the correct values by repeating the process of fig. 3.

Fig. 5 shows the procedure of the preheating monitoring process of the catalyst 36 according to the present embodiment. The process shown in fig. 5 is realized by the CPU72 repeatedly executing the monitoring process program 74b stored in the ROM74 shown in fig. 1 in association with the cold start of the internal combustion engine 10. The monitor handler 74b is repeatedly executed at a predetermined cycle until a determination of normality or abnormality is made, for example.

In the series of processes shown in fig. 5, the CPU72 first acquires the intake air amount Ga (S30). Then, the CPU72 updates the integrated value InGa by adding the intake air amount Ga obtained in the process of S30 to the integrated value InGa (S32). Then, the CPU72 determines whether the integrated value InGa is equal to or greater than a predetermined value Inth (S34). Here, the predetermined value Inth is set to an allowable upper limit value for bringing the temperature of the catalyst 36 to the reference temperature Tcatref if the warm-up control of the catalyst 36 is being normally performed. That is, when the intake air amount Ga is large, the fuel injection amount is increased as compared with when the intake air amount Ga is small, and the combustion energy generated in the combustion chamber 24 is also increased. Therefore, the total amount of heat received by the catalyst 36 also becomes large. Therefore, the cumulative value InGa reaching the predetermined value Inth can be set as the allowable upper limit time for the catalyst 36 to reach the reference temperature Tcatref. The reference temperature Tcatref is set in accordance with the temperature at which the catalyst 36 is activated.

When the CPU72 determines that the integrated value InGa is equal to or greater than the predetermined value Inth (S34: YES), it acquires the catalyst temperature Tcat (S36). Then, the CPU72 determines whether the catalyst temperature Tcat is lower than the reference temperature Tcatref (S38). This process is a process for determining whether or not the process shown in fig. 2 is not normally performed and an abnormality occurs in the warm-up control of the catalyst 36. The operation amount of the operation unit set by the abnormality determination monitoring control device 70, that is, the presence or absence of an abnormality of the command itself from the control device 70. In order to do so, the presence or absence of an abnormality in the warm-up control of the catalyst 36 is determined using an estimated value (Tcat) based on the operation amount for the warm-up processing.

When the CPU72 determines that the catalyst temperature Tcat is equal to or higher than the reference temperature Tcatref (no in S38), it makes a normal determination (S40). On the other hand, when the CPU72 determines that the catalyst temperature Tcat is lower than the reference temperature Tcatref (yes in S38), it determines that the warm-up control of the catalyst 36 is abnormal (S42). Then, the CPU72 executes a notification process for operating the warning lamp 98 shown in fig. 1 in order to urge the user to cope with the abnormality (S44).

Further, the CPU72 once ends the series of processing shown in fig. 5 when the processing of S40, S44 is completed or when a negative determination is made in the processing of S34.

Next, a method of generating the map data 76a will be described.

FIG. 6 illustrates a system that generates mapping data 76 a.

As shown in fig. 6, in the present embodiment, a dynamometer 100 is mechanically coupled to a crankshaft 30 of the internal combustion engine 10 via a torque converter 60 and a transmission 62. Various state variables during operation of the internal combustion engine 10 are detected by the sensor group 102, and the detection results are input to the adapter 104, which is a computer that generates the map data 76 a. The sensor group 102 includes an air flow meter 80, a crank angle sensor 82, an intake cam angle sensor 84, a water temperature sensor 88, and the like as sensors for detecting values for generating inputs to the map. The sensor group 102 includes temperature sensors for detecting the temperatures of the 1 st subregion a1, the 2 nd subregion a2, and the 3 rd subregion A3 of the catalyst 36.

Fig. 7 shows the steps of the generation processing of the mapping data. The process shown in fig. 7 is performed by the adaptation means 104. The processing shown in fig. 7 may be realized, for example, by providing the adapter device 104 with a CPU and a ROM, and executing a program stored in the ROM by the CPU.

In the series of processes shown in fig. 7, the adaptive device 104 first acquires, as training data, the same data as the data acquired in the process of S10 based on the detection results of the sensor group 102, and acquires, as teacher data in the training data, the 1 st temperature Tcat1t, the 2 nd temperature Tcat2t, and the 3 rd temperature Tcat3t which are the detection values of the temperature sensors (S50). The last letter t of Tcat1t represents teacher data.

Next, the adapter 104 executes the processing of S52 to S62, which are the same processing as the processing of S12 to S22, using training data other than teacher data.

Then, the CPU72 determines whether or not the number of samples of the 1 st temperature Tcat1, the 2 nd temperature Tcat2, and the 3 rd temperature Tcat3 calculated in the processes of S54, S58, and S62 is equal to or greater than a predetermined number (S64). Here, in order to set the number of samples to be equal to or greater than a predetermined number, it is required to calculate the 1 st temperature Tcat1, the 2 nd temperature Tcat2, and the 3 rd temperature Tcat3 at various operating points defined by the rotation speed NE and the air charging efficiency η by changing the operating state of the internal combustion engine 10.

If the adapter 104 determines that the number of samples is not equal to or greater than the predetermined number (no in S64), the process returns to S50. On the other hand, when the number of samples is determined to be equal to or greater than the predetermined number (yes in S64), the adaptive device 104 updates coefficients wF (1) ji, …, wF (α f)1p, coefficients wS (1) ji, …, wS (α S)1p, and coefficients wT (1) ji, …, wT (α t)1p (S66). Specifically, the adapter 104 updates the coefficients wF (1) ji, …, and wF (α f)1p so as to minimize the sum of squares of the differences between the 1 st temperature Tcat1t as teacher data and the 1 st temperature Tcat1 calculated in the processing of S54. The adapter 104 updates the coefficients wS (1) ji, …, wS (α S)1p so as to minimize the sum of squares of differences between the 2 nd temperature Tcat2t as teacher data and the 2 nd temperature Tcat2 calculated by the processing of S58. The adapter 104 updates the coefficients wT (1) ji, …, wT (α t)1p so as to minimize the sum of squares of differences between the 3 rd temperature Tcat3t as teacher data and the 3 rd temperature Tcat3 calculated in the processing of S62.

Then, the adaptation means 104 stores the coefficients wF (1) ji, …, wF (α f)1p, coefficients wS (1) ji, …, wS (α S)1p, coefficients wT (1) ji, …, wT (α t)1p as the learned mapping data 76a (S68).

Here, the operation and effect of the present embodiment will be described.

The CPU72 estimates the catalyst temperature Tcat based on the ignition timing average value aigave, the rotation speed NE, and the charging efficiency η, which are variables related to the operation amount of the ignition device 28, which is the operation unit of the internal combustion engine 10 used in the warm-up processing M42. The CPU72 determines that the warm-up control is abnormal when the catalyst temperature Tcat at which the integrated value InGa of the intake air amount Ga reaches the predetermined value Inth does not satisfy the reference temperature Tcatref. Here, the flow rate of the fluid flowing into the catalyst 36 is determined according to the rotation speed NE and the charging efficiency η, and the temperature of the fluid flowing into the catalyst 36 can be grasped by the ignition timing aig. Therefore, the catalyst temperature Tcat can be calculated with high accuracy. Therefore, the actual temperature of the catalyst 36 when the integrated value InGa reaches the predetermined value Inth can be expressed with high accuracy by the catalyst temperature Tcat. Therefore, in the process of determining an abnormality when the catalyst temperature Tcat does not satisfy the reference temperature Tcatref, the margin to be provided for the reference temperature Tcatref can be reduced as much as possible. Further, it is possible to suppress determination as an abnormality even if an abnormality does not actually occur.

According to the present embodiment described above, the following effects can be further obtained.

(1) The map input includes the rotation speed NE and the charging efficiency η that constitute operating point variables that define the operating point of the internal combustion engine 10. The operation amount of the operation portion of the internal combustion engine 10 tends to be variable depending on the operation point. Therefore, by setting the operating point variable as an input of the map, the catalyst temperature Tcat can be calculated reflecting the difference in the operation amount.

(2) The intake phase difference average DINave is included in the input to the map. The combustion temperature of the air-fuel mixture in the combustion chamber 24 changes according to the intake phase difference DIN, and the temperature of the exhaust gas discharged to the exhaust passage 34 changes. Therefore, by setting the intake air phase difference DIN as an input to the map, the catalyst temperature Tcat can be calculated with higher accuracy. In particular, in cold starting, the target intake phase difference DIN is not necessarily uniquely determined according to the operating point. Therefore, the catalyst temperature Tcat can be calculated with high accuracy by including the intake phase difference DIN in addition to the rotation speed NE and the charging efficiency η in the input to the map.

Incidentally, it is assumed that the target intake air phase difference DIN is uniquely determined by the rotation speed NE and the charging efficiency η and the water temperature THW. If so, by including the rotation speed NE, the charging efficiency η, and the water temperature THW as inputs to the map, it is possible to generate map data for calculating the catalyst temperature Tcat by reflecting the target intake air phase difference DIN by machine learning. However, in this case, the number of intermediate layers of the neural network becomes large, and the structure of the mapping becomes complicated. On the other hand, by including the intake phase difference DIN in the input to the map as in the present embodiment, it is possible to calculate the catalyst temperature Tcat reflecting the influence of the intake phase difference DIN with high accuracy while suppressing the complexity of the structure of the map.

(3) Instead of using ignition timing aig and intake phase difference DIN as inputs to the map, average values of these, that is, ignition timing average value aigave and intake phase difference average value DINave, are used as inputs to the map. Thus, the information of the ignition timing aig and the intake phase difference DIN can be taken into the map as much as possible without excessively shortening the cycle of the processing of fig. 3. Further, the catalyst temperature Tcat can be calculated with higher accuracy.

(4) The map of the catalyst temperature Tcat is learned and calculated by machine learning without arbitrarily inputting a large amount of various variables of the internal combustion engine 10. A variable having a large influence on the change in the catalyst temperature Tcat is selected. Therefore, compared to the case where the inventors' knowledge is not used, the number of layers in the intermediate layer of the neural network and the dimension of the input variable can be reduced, and the structure of the map for calculating the catalyst temperature Tcat can be easily simplified.

(5) Instead of constituting a single map of the output catalyst temperature Tcat, maps of the output 1 st temperature Tcat1, 2 nd temperature Tcat2, and 3 rd temperature Tcat3 are constituted, respectively. Further, by assuming that "i" is 2 or 3 "and estimating the i-th temperature Tcati based on the" i-1 "temperature average value Tcat" i-1 "ave," the i-th temperature Tcati can be estimated in consideration of heat exchange between the i-th partial region Ai and the "i-1" partial region a "i-1". Therefore, as compared with the case where the map for the output catalyst temperature Tcat is formed by a single map, for example, heat exchange between partial regions of the catalyst 36 can be reflected easily. Therefore, the structure of each map can be simplified, and the accuracy of estimating the temperature can be improved.

< embodiment 2 >

Hereinafter, embodiment 2 will be described mainly with reference to fig. 8 and 9, focusing on differences from embodiment 1.

Fig. 8 shows a part of the processing executed by the control device 70 of the present embodiment. The process shown in fig. 8 is realized by the CPU72 executing a program stored in the ROM 74. Note that, in fig. 8, the same reference numerals are given to the processes corresponding to those shown in fig. 2 for convenience. Hereinafter, the internal combustion engine 10 will be described as having 4 cylinders, i.e., the cylinders #1 to # 4.

The amplitude value variable output process M50 sets the air-fuel ratio as the target air-fuel ratio when the air-fuel mixtures to be burned, i.e., the air-fuel mixtures in each of the cylinders #1 to #4, are collected into 1 during 2 revolutions of the crankshaft 30. Amplitude value variable output processing M50 is processing for calculating and outputting amplitude value α of dither control for making the air-fuel ratio of the air-fuel mixture to be burned different among cylinders, assuming such a target air-fuel ratio. Here, in the dither control according to the present embodiment, 1 cylinder out of the 1 st cylinder #1 to the 4 th cylinder #4 is set as a rich combustion cylinder in which the air-fuel ratio of the mixture is made richer than the stoichiometric air-fuel ratio, and the remaining 3 cylinders are set as lean combustion cylinders in which the air-fuel ratio of the mixture is made leaner than the stoichiometric air-fuel ratio. The injection amount in the rich-burn cylinder is set to "1 + α" times the required injection amount Qd, and the injection amount in the lean-burn cylinder is set to "1- (α/3)" times the required injection amount Qd. Thus, if the same amount of air is filled into each of the cylinders #1 to #4 in the 1 combustion cycle, the following 2 values (v) and (vi) are equal to each other.

The value (v) is the sum of the number of occurrences of the combustion stroke of the rich-burn cylinder during 2 revolutions of the crankshaft (here, 1 time) relative to the increment ratio of the required injection amount Qd (here, "α") in the rich-burn cylinder (here, "α" itself).

The value (vi) is the sum of the number of occurrences of the combustion stroke of the lean burn cylinder during 2 revolutions of the crankshaft (here, 3 times) of the decrement ratio (here, "α/3") with respect to the required injection amount Qd in the lean burn cylinder (here, "α" itself).

By making the value (v) and the value (vi) equal to each other, if the amount of air to be filled into each of the cylinders #1 to #4 is the same in 1 combustion cycle, the air-fuel ratio when the air-fuel mixtures to be burned are collected into 1 in each of the cylinders #1 to #4 of the internal combustion engine 10 can be made the same as the target air-fuel ratio.

In the cold start of the internal combustion engine 10, a warm-up request of the catalyst 36 is generated. Therefore, amplitude value α is set to a value greater than zero by amplitude value variable output processing M50. Specifically, the amplitude value variable output process M50 includes a process of variably setting the amplitude value α based on the rotation speed NE and the inflation efficiency η. Specifically, in a state where mapping data having the rotation speed NE and the inflation efficiency η as input variables and the amplitude value α as an output variable is stored in the ROM74 in advance, the CPU72 performs mapping operation on the amplitude value α. Incidentally, fig. 8 illustrates that the amplitude value α is zero in a region where the rotation speed NE and the inflation efficiency η are large. This is because, in a high load region or the like, the energy flow rate of the exhaust gas flowing into the catalyst 36 becomes large even if the dither control is not executed.

The mapping data is a data set of discrete values of the input variable and values of the output variable corresponding to the values of the input variable. The mapping operation may be, for example, the following processing: when the value of the input variable matches any one of the values of the input variables of the map data, the value of the output variable of the corresponding map data is used as the calculation result, and when the values of the input variables do not match, the value obtained by interpolation of the values of the plurality of output variables included in the map data is used as the calculation result.

The correction coefficient calculation process M52 is a process of calculating a correction coefficient of the required injection amount Qd for the rich-burn cylinder by adding the amplitude value α to "1". The shake correction process M54 is a process of calculating the injection amount command value Q of the cylinder # w set to the rich-burn cylinder by multiplying the required injection amount Qd by the correction coefficient "1 + α". Here, "w" means any one of "1" to "4".

The multiplication process M56 is a process of multiplying the amplitude value α by "-1/3", and the correction coefficient calculation process M58 is a process of calculating a correction coefficient of the required injection amount Qd for the lean burn cylinder by adding the output value of the multiplication process M56 to "1". The shake correction process M60 is a process of calculating an injection amount command value Q for each of the cylinders # x, # y, # z to be lean burn cylinders by multiplying the required injection amount Qd by the correction coefficient "1- (α/3)". Here, "x", "y", and "z" are any of "1" to "4", and "w", "x", "y", and "z" are different from each other.

The injection valve operation process M30 outputs operation signals MS2 and MS3 to the port injection valve 16 and the in-cylinder injection valve 26 of the cylinder # w set as the rich-burn cylinder, based on the injection quantity command value Q output by the shake correction process M54. In this way, the total amount of fuel injected from port injection valve 16 and in-cylinder injection valve 26 is set to an amount corresponding to injection quantity command value Q. In addition, the injection valve operation process M30 outputs operation signals MS2 and MS3 to the port injection valves 16 and the in-cylinder injection valves 26 of the cylinders # x, # y, # z, which are lean burn cylinders, based on the injection quantity command value Q output by the shake correction process M60. In this way, the total amount of fuel injected from port injection valve 16 and in-cylinder injection valve 26 is set to an amount corresponding to injection quantity command value Q.

In the present embodiment, the preheating process M42 is configured by an amplitude value variable output process M50, a correction coefficient calculation process M52, a shake correction process M54, a multiplication process M56, a correction coefficient calculation process M58, a shake correction process M60, and an injection valve operation process M30.

Fig. 9 shows the procedure of the estimation process of the temperature of the catalyst 36. The process shown in fig. 9 is realized by the CPU72 repeatedly executing the temperature estimation program 74a stored in the ROM74 shown in fig. 1, for example, at predetermined cycles. Note that, in fig. 9, the same step numbers are given to the processes corresponding to the processes shown in fig. 3 for convenience.

In the series of processes shown in fig. 9, the CPU72 first executes a process of changing the acquisition of the ignition timing average value aigave to the acquisition of the amplitude value average value α ave with respect to the process of S10 (S10 a). Here, amplitude value average value α ave is an average value of amplitude values α in the cycle of the processing of S10 a. Next, the CPU72 performs a process of changing the variable substituted for the input variable x (3) from the ignition timing average value aigave to the amplitude value average value α ave with respect to the process of S12 (S12 a). Then, the CPU72 executes the same processing as S16 to S24 in fig. 3, except that the input variable x (3) is changed.

In this way, in the present embodiment, the dither control is executed as the warm-up processing M42. According to the dither control, warm-up of the catalyst 36 is promoted by heat generated when oxygen discharged from the lean-burn cylinder is stored in the catalyst 36 and oxidation heat of oxidation of oxygen stored in the catalyst 36 by unburned fuel discharged from the rich-burn cylinder. Therefore, by including the amplitude value average value α ave in the input of the map, the temperature of the catalyst 36 can be calculated with high accuracy.

< embodiment 3 >

Hereinafter, embodiment 3 will be described with reference to fig. 10 focusing on differences from embodiment 1.

Fig. 10 shows the procedure of the estimation process of the temperature of the catalyst 36. The process shown in fig. 10 is realized by the CPU72 repeatedly executing the temperature estimation program 74a stored in the ROM74 shown in fig. 1, for example, at predetermined cycles. Note that, in fig. 10, the same step numbers are assigned to the processes corresponding to the processes shown in fig. 3 for convenience.

In the series of processes shown in fig. 10, the CPU72 first acquires the incremental quantity average value Qiave, the injection distribution ratio average value Kpave, the EGR ratio average value Regrave, the atmospheric pressure Pa, and the flow rate variable QF in addition to the variables acquired in the process of S10 (S10 b). Here, the increase amount average value Qiave, the injection distribution ratio average value Kpave, and the EGR ratio average value Regr are average values of the increase amount Qi, the injection distribution ratio Kp, and the EGR ratio Regr in the processing cycle of S10 b. The increase amount Qi represents an excessive shortage with respect to the amount of fuel required to make the air-fuel ratio of the mixture stoichiometric. The flow rate variable QF is a variable indicating the flow rate of the coolant in the coolant circulation path 52, and is calculated by the CPU72 based on the opening degree of the flow rate control valve 56.

Next, the CPU72 generates the input variables x (1) to x (5) in the same manner as in the processing of S12, and also generates the input variables x (6) to x (11) (S12 b). That is, the CPU72 substitutes the incremental amount average value Qiave for the input variable x (6), substitutes the injection distribution ratio average value Kpave for the input variable x (7), and substitutes the EGR ratio average value Regrave for the input variable x (8). The CPU72 substitutes the atmospheric pressure Pa for the input variable x (9), the flow rate variable QF for the input variable x (10), and the previous value of the 1 st temperature Tcat1 for the input variable x (11).

Next, the CPU72 calculates a1 st temperature Tcat1 by inputting the input variables x (1) to x (11) to a map that outputs a1 st temperature Tcat1(S14 b). The mapping here is a neural network similar to the neural network used in the processing of S14, but the dimensions of the input variables are different.

Next, the CPU72 generates input variables x (1) to x (12) that output the map of the 2 nd temperature Tcat2 (S16 b). Here, the input variables x (1) to x (10) are the same as the input variables x (1) to x (10) generated in the processing of S12 b. The CPU72 substitutes the last value of the 2 nd temperature Tcat2 for the input variable x (11), and substitutes the 1 st temperature average value Tcat1ave for the input variable x (12).

Next, the CPU72 calculates a2 nd temperature Tcat2 by inputting the input variables x (1) to x (12) to a map that outputs a2 nd temperature Tcat2(S18 b). The mapping here is a neural network similar to the neural network used in the processing of S18, but the dimensions of the input variables are different.

Next, the CPU72 generates input variables x (1) to x (12) that output the map of the 3 rd temperature Tcat3 (S20 b). Here, the input variables x (1) to x (10) are the same as the input variables x (1) to x (10) generated in the processing of S12 b. The CPU72 substitutes the last value of the 3 rd temperature Tcat3 for the input variable x (11), and substitutes the 2 nd temperature average value Tcat2ave for the input variable x (12).

Next, the CPU72 calculates a3 rd temperature Tcat3 by inputting the input variables x (1) to x (12) to a map that outputs a3 rd temperature Tcat3(S22 b). The mapping here is a neural network similar to the neural network used in the processing of S22, but the dimensions of the input variables are different.

Then, the CPU72 moves to the process of S24.

According to the present embodiment described above, the following effects can be obtained.

(6) The delta quantity average value Qiave is included in the input to the map. For example, when the injection amount is set by the start-time injection amount setting process M28, the injection amount is not determined according to the operating point of the internal combustion engine 10. Therefore, for example, the injection amount cannot be accurately grasped by simply inputting the operation point. In addition, since the temperature increase coefficient Kw is a value larger than "1" during cold start, the injection amount is not uniquely determined depending on the operating point of the internal combustion engine 10. Therefore, the injection amount cannot be accurately grasped only by inputting the operation point. In contrast, in the present embodiment, by using the incremental amount average value Qiave, the injection amount can be accurately grasped, and the catalyst temperature Tcat can be accurately calculated.

In the present embodiment, the information on the injection amount in consideration of the influence of the low temperature increase coefficient Kw can be obtained in principle from the rotation speed NE, the charging efficiency η, and the water temperature THW. In this case, in order to calculate the catalyst temperature Tcat in consideration of the influence of the low temperature increase coefficient Kw, it is considered that the structure of the map is likely to be complicated, for example, the number of layers of the intermediate layer is increased. On the other hand, by using the increase amount average value Qiave, the influence of the low temperature increase coefficient Kw can be grasped, the catalyst temperature Tcat can be calculated with high accuracy, and the structure of the map can be simplified.

(7) Included among the inputs to the map are injection distribution ratio average values Kpave. This makes it possible to calculate catalyst temperature Tcat reflecting the difference in combustion between the case where fuel is injected from port injection valve 16 and the case where fuel is injected from in-cylinder injection valve 26.

(8) The EGR rate average value Regrave is included in the input to the map. This makes it possible to calculate the catalyst temperature Tcat reflecting the difference in temperature of the exhaust gas discharged to the exhaust passage 34 due to the difference in combustion when the EGR rate Regr is different.

(9) The atmospheric pressure Pa is included in the input to the map. This makes it possible to calculate the catalyst temperature Tcat reflecting the combustion difference according to the atmospheric pressure Pa.

(10) Included in the input to the map is a flow variable QF. This makes it possible to calculate the catalyst temperature Tcat reflecting the temperature change of the coolant due to the heat exchange amount between the coolant and the temperature control device 54, and further, the temperature change of each part of the internal combustion engine 10.

< embodiment 4 >

Hereinafter, embodiment 4 will be described mainly with reference to fig. 11, focusing on differences from embodiment 1.

Fig. 11 shows the procedure of the estimation process of the temperature of the catalyst 36. The process shown in fig. 11 is realized by the CPU72 repeatedly executing a temperature estimation program 74a stored in the ROM74 shown in fig. 1, for example, at predetermined cycles.

In the series of processing shown in fig. 11, the CPU72 first acquires previous values of the rotation speed NE, the charging efficiency η, the ignition timing average value aigave, the intake phase difference average value DINave, the water temperature THW, the intake air amount Ga, and the catalyst temperature Tcat (S70). Then, the CPU72 substitutes variables other than the last value of the catalyst temperature Tcat among the variables acquired through the processing of S70 into the input variables x (1) to x (5) (S72). Here, the input variables x (1) to x (5) are the same as those in S12.

Next, the CPU72 calculates the stable temperature Tcats by inputting the input variables x (1) to x (5) to a map that outputs the stable temperature Tcats (S74). Here, the steady temperature Tcats is the temperature of the catalyst 36 in a steady state such as when the amount of change in the operating point variable of the internal combustion engine 10 is equal to or less than a predetermined value.

The mapping consists of a neural network where the middle layer is layer 1 and the activation function h1 of the middle layer is a hyperbolic tangent function and the activation function f of the output layer is a ReLU. For example, the value of each node in the intermediate layer is generated by inputting the output when the input variables x (1) to x (5) are input to the activation function h1, in a linear map defined by coefficients w (1) ji (j is 0 to n1, i is 0 to 5). Incidentally, wj0 and the like are bias parameters, and the input variable x (0) is defined as "1".

The map data defining the map may be generated based on training data obtained when the internal combustion engine 10 is operated stably at each of the plurality of operating points, for example.

Next, the CPU72 calculates a time constant β for making the catalyst temperature Tcat transition to the stable temperature Tcats based on a map formed by a linear regression equation having as input the intake air amount Ga and a value obtained by subtracting the catalyst temperature Tcat from the stable temperature Tcats (S76). The linear regression equation may be a linear regression equation obtained by measuring a behavior until the actual temperature is changed to the stable temperature and learning the behavior as teacher data, for example.

Then, the CPU72 updates the catalyst temperature Tcat using the sum of the value obtained by multiplying the stable temperature Tcats by the time constant β and the value obtained by multiplying the last value of the catalyst temperature Tcat by "1- β" (S78).

Further, the CPU72 once ends the series of processing shown in fig. 11 when the processing of S78 is completed.

As described above, in the present embodiment, the catalyst temperature Tcat is calculated using the map for calculating the stable temperature Tcats and the map for calculating the time constant β. This can reduce the requirement for each map. Therefore, for example, compared to a single map that outputs the catalyst temperature Tcat, the structure of each map can be simplified, and the temperature can be calculated with high accuracy.

(11) Instead of setting the input of the map of the output time constant β as 3 parameters of the intake air amount Ga, the stable temperature Tcats, and the catalyst temperature Tcat, 2 parameters of the intake air amount Ga and a value obtained by subtracting the catalyst temperature Tcat from the stable temperature Tcats are set. The inventors have made use of the finding that the time constant β corresponds to the difference between the stabilization temperature Tcats and the catalyst temperature Tcat. This can reduce the number of elements to be learned by machine learning, and thus can simplify the mapping.

< embodiment 5 >

Hereinafter, embodiment 5 will be described with reference to fig. 12, focusing on differences from embodiment 1.

In the present embodiment, the process of calculating the catalyst temperature Tcat is performed outside the vehicle.

Fig. 12 shows a catalyst warm-up monitoring system according to the present embodiment. In fig. 12, members corresponding to those shown in fig. 1 are denoted by the same reference numerals for convenience.

The control device 70 in the vehicle VC shown in fig. 12 includes a communication device 79. Communicator 79 is a device for communicating with center 120 via network 110 outside of vehicle VC.

The center 120 parses data sent from a plurality of vehicles VC. The center 120 includes a CPU122, a ROM124, a storage device 126, a peripheral circuit 127, and a communicator 129, and can communicate with each other through a local network 128. The ROM124 stores a temperature estimation main program 124a, and the storage device 126 stores mapping data 126 a.

FIG. 13 illustrates steps of a process performed by the system shown in FIG. 12. The processing shown in part (a) of fig. 13 is realized by the CPU72 executing the temperature estimation subroutine 74c stored in the ROM74 shown in fig. 12. The processing shown in part (b) of fig. 13 is realized by the CPU122 executing the temperature estimation main program 124a stored in the ROM 124. The processing shown in fig. 13 is described below along the sequence of the temperature estimation processing.

As shown in part (a) of fig. 13, in the vehicle VC, the CPU72 first acquires some variables that are inputs of the map, in addition to variables other than the last value of the 1 st temperature Tcat1, the last value of the 2 nd temperature Tcat2, and the last value of the 3 rd temperature Tcat3 among the variables acquired in the process of S10b (S10 d). That is, the CPU72 obtains, as a specification variable that is a variable indicating the specification among the state variables of the catalyst 36, the maximum value Cmax of the oxygen storage amount at the reference temperature, the length Lud of the catalyst 36 from the upstream side to the downstream side, and the precious metal supporting amount Qpm of the catalyst 36. This is a setting for calculating the temperatures of the catalysts 36 of various specifications using one map data.

Next, the CPU72 transmits the data acquired through the processing of S10d to the center 120 together with the vehicle ID, which is data indicating the identification information of the vehicle (S80).

On the other hand, as shown in fig. 13 b, the CPU122 of the center 120 receives the transmitted data (S90), and substitutes the data acquired through the processing of S90 into the mapped input variable x (S12 d). Here, the CPU122 substitutes the same variables as those in the processing of S12b for the input variables x (1) to x (10). The CPU122 substitutes the last value of the catalyst temperature Tcat for the input variable x (11), the maximum value Cmax for the input variable x (12), the length Lud for the input variable x (13), and the supporting amount Qpm for the input variable x (14).

Then, the CPU122 calculates the catalyst temperature Tcat by inputting the input variables x (1) to x (14) generated in S12d to the map defined by the map data 126a (S14 d). The map is composed of a neural network in which the number of intermediate layers is "α", the activation functions h1 to h α of the intermediate layers are hyperbolic tangent functions, and the activation function f of the output layer is ReLU. For example, the value of each node in the 1 st intermediate layer is generated by inputting the output when the input variables x (1) to x (14) are input to the activation function h1, in a linear map defined by coefficients w (1) ji (j is 0 to n1, i is 0 to 14). That is, when m is 1, 2, …, or α, the value of each node in the mth intermediate level is generated by inputting the output of the linear map defined by the coefficient w (m) to the activation function hm. Here, n1, n2, …, and n α are the number of nodes in the 1 st, 2 nd, … th, and α th intermediate layers, respectively. Incidentally, w (1) j0 and the like are bias parameters, and the input variable x (0) is defined as "1".

Then, the CPU122 transmits a signal relating to the catalyst temperature Tcat to the vehicle VC, which is the transmission source of the data received through the processing of S90, by operating the communicator 129 (S92), and once ends the series of processing shown in part (b) of fig. 13. In contrast, as shown in part (a) of fig. 13, the CPU72 receives the catalyst temperature Tcat (S82), and once ends the series of processing shown in part (a) of fig. 13.

As described above, according to the present embodiment, the calculation load of the control device 70 can be reduced by calculating the catalyst temperature Tcat at the center 120.

< correspondence relationship >

The correspondence between the matters in the above embodiment and the matters described in the above section of "summary of the invention" is as follows. In the following, the correspondence relationship is shown for each number of the example described in the column of "contents of the invention".

[1] The catalyst [11] corresponds to the catalyst 36. The execution devices correspond to the CPU72 and the ROM 74. The warm-up operation amount variables correspond to the ignition timing average value aigave, and the amplitude value average value α ave. The correspondence relation data corresponds to data defining the processing of S30 to S42. The acquisition processing corresponds to the processing of S10, S10a, S10b, S70.

The temperature calculation process corresponds to the processes of S12 to S24, the processes of S12a and S14 to S24, the processes of S12b to S22b and S24, and the processes of S72 to S78. The determination processing corresponds to the processing of S30 to S42. The coping process corresponds to the process of S44. The predetermined hardware corresponds to the warning lamp 98.

[2] The valve characteristic variable device corresponds to the variable valve timing device 44. The valve characteristic variable corresponds to the intake phase difference average value DINave.

[3] The ignition variable corresponds to the ignition timing average value aigave.

[4] The injection amount corresponds to the increment amount average value Qiave and the amplitude value average value α ave.

[5] The amplitude value variation corresponds to the amplitude value average value α ave.

[6] The injection distribution variable corresponds to the injection distribution ratio average value Kpave.

[7] The EGR variable corresponds to the average EGR rate value Regrave.

[8] The atmospheric pressure variable corresponds to atmospheric pressure Pa.

[9] The regulating device corresponds to the flow control valve 56 and the flow variable corresponds to the flow variable QF.

[10] N corresponds to "3".

[11] The stable map corresponds to the map used in the process of S74. The air amount variable corresponds to the intake air amount Ga. The time constant calculation process corresponds to the process of S76.

[13] The catalyst warm-up monitoring system corresponds to the control device 70 and the center 120. The 1 st execution device corresponds to the CPU72 and the ROM 74. The 2 nd execution means corresponds to the CPU122 and the ROM 124. The acquisition processing corresponds to the processing of S10d, the vehicle-side transmission processing corresponds to the processing of S80, and the vehicle-side reception processing corresponds to the processing of S82. The outside-side reception process corresponds to the process of S90. The temperature calculation process corresponds to the processes of S12d and S14 d. The outside-side transmission process corresponds to the process of S92.

[14] The data parsing means corresponds to the center 120.

[15] The control device of the internal combustion engine corresponds to the control device 70.

[16] The receiving device may be constituted by a portable information terminal or a vehicle-mounted communication device adapted to execute application software for receiving information. Such a reception device is hardware constituting a part of the catalyst warm-up monitoring system, and is configured to execute the vehicle-side reception process S82.

< other embodiment >

The present embodiment can be modified and implemented as follows. This embodiment and the following modifications can be combined and implemented within a range not technically contradictory to the technology.

"about ignition variables"

In the above embodiment, the ignition timing average value aigave is exemplified as the ignition variable, but the present invention is not limited thereto. For example, ignition timing aig may be an ignition variable.

"variables relating to valve characteristics"

In the above embodiment, the intake air phase difference average value DINave is used as the valve characteristic variable, but the present invention is not limited thereto, and for example, an average value of the target intake air phase difference DIN may be used. In addition, for example, a single sampled value of the intake phase difference DIN or the target intake phase difference DIN may be used as the valve characteristic variable. In the case where a device for varying the lift amount is used as the valve characteristic varying device as described in the column of "valve characteristic varying device" below, a target value or a detected value of the lift amount or the like is used as the valve characteristic variable.

"variable concerning injection quantity"

The excess variable, which is a variable indicating the excess of the actual fuel amount with respect to the fuel amount that reacts little by little with the oxygen in the exhaust gas discharged to the exhaust passage 34, is not limited to the increase amount average value Qiave, and may be, for example, the increase amount Qi itself. The excess amount variable may be constituted by the base injection amount Qb and an increase ratio obtained by dividing the increase amount Qi by the base injection amount Qb, or an average value of the increase ratios. The excess variable may be constituted by, for example, an increase ratio or an average value of the increase ratio, the intake air amount Ga, and the rotation speed NE. The excess variable may be constituted by an increment ratio or an average of increment ratios, and the inflation efficiency η, for example.

The injection amount variable is not limited to the excess amount variable, and may be, for example, a required injection amount Qd or an average value of the required injection amount Qd.

"variable concerning spray distribution"

The injection distribution variable is not limited to the injection distribution ratio average value Kpave, and may be, for example, the injection distribution ratio Kp itself.

"relating to EGR variables"

The EGR variable is not limited to the EGR rate average value Regrave, and may be, for example, an EGR rate Regr.

"about variation of amplitude value"

The amplitude value variable is not limited to the amplitude value average value α ave, and may be, for example, the amplitude value α itself. Further, for example, the difference between the injection amount command value for the rich-burn cylinder and the injection amount command value for the lean-burn cylinder or the average value of the differences may be used.

"variable concerning preheating operation amount"

In the above embodiment, when the dither control is performed, the preheating process is configured by only the dither control, but the present invention is not limited to this. For example, the spark timing may be retarded by a predetermined amount from the normal time while the dither control is being performed. In this case, the preheating operation amount used for the preheating process is both amplitude value α and ignition timing aig.

"about action Point variables"

The operating point variables are not limited to the rotation speed NE and the inflation efficiency η. For example, the intake air amount Ga and the rotation speed NE may be used. Instead of setting the intake air amount Ga as an input to the map, the operating point variable may not be set as an input to the map.

For example, instead of setting the intake air amount Ga as an input to the map, the operating point variable may not be set as an input to the map. Further, even when the internal combustion engine 10 is mounted on a series hybrid vehicle and the internal combustion engine 10 is driven only at a predetermined operating point as described in the column of "vehicle" below, for example, it is not necessary to set the operating point variable as an input of the map.

"about cyclic path, regulating means"

The circulation path is not limited to a circulation path of cooling water. For example, the circulation path of the lubricating oil of the internal combustion engine 10 may be a circulation path. In addition, both the circulation path of the cooling water and the circulation path of the lubricating oil may be circulation paths.

"about a part of a region"

In the above embodiment, the example in which the catalyst to be estimated of the temperature is divided into 3 partial regions is shown, but the present invention is not limited to this. For example, the division may be performed into 2 partial regions, or may be performed into 4 or more partial regions.

"input on mapping"

(a) Input on mapping of partial regions

The input for outputting each map of the 1 st to nth temperatures is not limited to include all the variables illustrated in the processing of S12.

For example, in the above embodiment, the 1 st temperature average value tcave, which is an input of the map outputting the 2 nd temperature Tcat2, is calculated to include the current value of the 1 st temperature Tcat1, but the present invention is not limited thereto. Note that, instead of including the 1 st temperature average value Tcat1ave in the input of the map that outputs the 2 nd temperature Tcat2, a present value, a previous value, and the like of the 1 st temperature Tcat1 may be included. Note that the input of the map for outputting the 3 rd temperature Tcat3 and the like may be changed in the same manner as the input of the map for outputting the 2 nd temperature Tcat 2.

For example, an exhaust gas temperature sensor that detects an exhaust gas temperature may be provided upstream of the catalyst 36, and the detected value may be included in the input of the map that outputs the 1 st temperature Tcat 1. Further, for example, "i" may be an integer of 2 or more, and the input of the map for outputting the i-th temperature Tcati may include time-series data of the "i-1" th temperature Tcat "i-1". In addition. For example, the detected value of the exhaust gas temperature or the average value thereof may be included in the input of the map that outputs the i-th temperature Tcati.

For example, "i" may be 1 to N-1, and the "i + 1" th temperature Tcat "i + 1" may be included in the input of the map to output the i-th temperature Tcati.

(b) Input to a map of output stabilization temperatures

The input of the map for outputting the stable temperature is not limited to all the processing illustrated in S72.

(c) Input regarding the mapping used by hub 120

In the processing of S12d, not all of the illustrated input variables need to be input variables. For example, the maximum value Cmax, the length Lud from the upstream to the downstream, and the supported amount Qpm may be 3, or 1 or more of them may be included to constitute the specification variables of the catalyst, and these may be used as the input variables. Of course, it is not necessary to set the specification variables as inputs to the map.

(d) Input for mapping used in vehicle VC

The input variables illustrated in the processing at S12d, which are not included in the map used in the vehicle VC in the above embodiment, may be included in the map used in the vehicle VC.

(e) Others

For example, the vehicle speed SPD may be included as an input of the map.

For example, the map may include a storage amount variable, which is a variable relating to the oxygen storage amount in each region from the upstream side to the downstream side of the catalyst to be estimated, as an input of the map. The storage amount variable can be calculated by, for example, calculating an increase/decrease amount of the oxygen storage amount and updating the storage amount by the increase/decrease amount. First, the amount of increase and decrease is mapped based on the air-fuel ratio Af and the intake air amount Ga in the most upstream region. Then, the amount of increase or decrease in the oxygen storage amount in the downstream region adjacent to the most upstream region is mapped based on the air-fuel ratio Af, the amount of increase or decrease in the most upstream region, and the intake air amount Ga. Then, based on the air-fuel ratio Af, the sum of the increase/decrease amounts in the most upstream region and the region adjacent thereto, and the intake air amount Ga, the increase/decrease amount of the downstream region adjacent to the most upstream region is subjected to map calculation. Hereinafter, similarly, the increase/decrease amount of the target region is mapped based on the sum of the increase/decrease amounts of all regions upstream of the target region, the air-fuel ratio Af, and the intake air amount Ga.

For example, as described in the column of "internal combustion engine" below, when the internal combustion engine 10 includes a supercharger, a bypass path for allowing exhaust gas to flow into the catalyst 36 while bypassing the supercharger, and a valve for adjusting the flow path cross-sectional area of the bypass path, the opening degree of the valve or the average value of the opening degrees may be included in the input of the map. Of course, even when the internal combustion engine 10 is provided with a supercharger, the opening degree or the average value of the opening degrees is not necessarily included.

For example, instead of using the single sampling values of the preheating operation amount variable such as the ignition timing average value aigave, the rotation speed NE, and the charging efficiency η as inputs to the map, time series data thereof may be used as inputs to the map.

"mapping with respect to time constant"

The map of the output time constant β illustrated in fig. 11 is not limited to being determined according to the linear regression equation. For example, the time constant β may be an output obtained by inputting the output of the linear regression equation illustrated in fig. 11 to a nonlinear function. Of course, not limited to this, for example, a neural network that outputs the time constant β may be used. Here, the input variable to the neural network may be a difference between the intake air amount Ga and the stable temperature Tcats and the catalyst temperature Tcat, but may include 3 of the intake air amount Ga, the stable temperature Tcats, and the catalyst temperature Tcat. Further, the output time constant map may be configured using map data, for example, without being limited to including a learned model based on machine learning.

"about mapping data"

In the above embodiment, activation functions h1, h2, … h α f, h1, h2, … h α s, h1, h2, … h α t, h1, h2, and … h α are hyperbolic tangent functions, and activation function f is ReLU, but the present invention is not limited thereto. For example, the activation functions h1, h2, … h α f, h1, h2, … h α s, h1, h2, … h α t, h1, h2, and … h α may be set as ReLU. For example, the activation functions h1, h2, … h α f, h1, h2, … h α s, h1, h2, … h α t, h1, h2, and … h α may be set as Logistic Sigmoid functions. The activation function f may be, for example, a Logistic Sigmoid function, a hyperbolic tangent function, or an identity map.

The mapping data is not limited to data learned by machine learning. This can be achieved by adapting the map data having the input variables x (1) to x (5) in the process of S72 as input variables and the stable temperature Tcats as output variables in the process of fig. 11, for example. However, performing machine learning easily reduces adaptation man-hours compared to adapting mapping data.

In fig. 3, 9, 10, and 13, the number of intermediate layers of the neural network is more than 2, but the neural network is not limited to this, and the intermediate layers may be 1 layer or 2 layers. In particular, when the temperature of each part region of the catalyst 36 is calculated as shown in fig. 3, 9, and 10, it is easy to calculate the catalyst temperature Tcat with high accuracy and simplify the structure of each neural network, and therefore, it is preferable to set the catalyst temperature Tcat to 2 layers or less, and more preferably 1 layer.

"Generation of mapping data"

In the above embodiment, data obtained when the internal combustion engine 10 is operated with the dynamometer 100 connected to the crankshaft 30 via the torque converter 60 and the transmission 62 is used as training data, but the present invention is not limited thereto. For example, data obtained when the internal combustion engine 10 is driven with the internal combustion engine 10 mounted on the vehicle VC may be used as the training data.

"with respect to temperature calculation processing"

In the processing of S24, although the catalyst temperature Tcat is set to the 2 nd temperature Tcat2 as an example, it is not always necessary to set the catalyst temperature Tcat to the temperature of the partial region in the center of the partial region from the upstream side to the downstream side of the catalyst 36. For example, the temperature of the partial region of the end portion on the upstream side of the catalyst 36 may be set as the catalyst temperature Tcat. For example, the average value of the temperatures of all the partial regions of the catalyst 36 may be set as the catalyst temperature Tcat, the lowest value of the temperatures of all the partial regions may be set as the catalyst temperature Tcat, or the highest value of the temperatures of all the partial regions may be set as the catalyst temperature Tcat.

"treatment of deals"

The notification process is not limited to the operation of a device that outputs visual information such as the warning lamp 98, and may be, for example, a process of operating a device that outputs voice information.

The coping process is not limited to the notification process. For example, a sensor that detects the temperature of the exhaust gas flowing into the catalyst 36 may be provided, and when it is determined that there is an abnormality, the feedback control may be performed such that the detection value of the sensor becomes equal to or higher than a predetermined temperature.

"about data parsing device"

When the catalyst temperature Tcat is calculated in the center 120, the processes illustrated in, for example, the processes of S12 to S24, the processes of S12a, S14 to S24, the processes of S12b to S22b, S24, the processes of S72 to S78, and modifications thereof may be performed instead of the processes of S12d, 14 d.

The process of part (b) of fig. 13 may be executed by a mobile terminal held by the user, for example.

"about the actuator"

The execution device is not limited to the one provided with the CPU72(122) and the ROM74(124) and executes software processing. For example, a dedicated hardware circuit (e.g., ASIC) may be provided for performing hardware processing on at least a part of the software processing in the above embodiment. That is, the actuator may be configured as any one of the following (a) to (c). (a) The program storage device (including a non-transitory computer-readable storage medium) includes a processing device that executes all of the above-described processes in accordance with a program, and a program storage device (such as a ROM) that stores the program. (b) The apparatus includes a processing device and a program storage device for executing a part of the above-described processing in accordance with a program, and a dedicated hardware circuit for executing the remaining processing. (c) The apparatus includes a dedicated hardware circuit for executing all of the above-described processing. Here, the software executing apparatus and the dedicated hardware circuit provided with the processing apparatus and the program storage apparatus may be plural ones.

"about storage device"

In the above embodiment, the storage device storing the

map data

76a, 126a is provided as a storage device different from the storage devices (ROMs 74, 124) storing the temperature estimation program 74a and the temperature estimation main program 124a, but is not limited thereto.

Devices relating to variation of valve characteristics "

The valve characteristic varying device that varies the characteristic of the intake valve 18 is not limited to the variable valve timing device 44. For example, the lift amount of the intake valve 18 may be changed. In this case, the parameter indicating the valve characteristics of the intake valve 18 is a lift amount or the like instead of the intake phase difference DIN.

"relating to internal combustion engines"

The internal combustion engine does not necessarily have to be provided with a supercharger.

The internal combustion engine is not limited to being provided with both of port injection valve 16 and in-cylinder injection valve 26, and may be provided with only one of these 2 types of fuel injection valves.

It is not necessary that the internal combustion engine constitutes the drive system itself. For example, the present invention may be mounted on a so-called series hybrid vehicle in which a crankshaft is mechanically coupled to a vehicle-mounted power generator and power transmission to drive wheels 64 is cut off.

"about vehicle"

The vehicle is not limited to a vehicle in which the device for generating the propulsion of the vehicle is an internal combustion engine only, and may be a parallel hybrid vehicle or a hybrid vehicle, for example, in addition to the series hybrid vehicle described in the column "related to the internal combustion engine".

Claims

1. A catalyst warm-up monitoring device for an internal combustion engine, comprising an execution device and a storage device,

the catalyst warm-up monitoring device is applied to an internal combustion engine having a catalyst in an exhaust passage,

the storage device is configured to store map data defining a map in which an estimated value of the temperature of the catalyst is input and output with a previous value of a warm-up operation amount variable and an estimated value of the temperature of the catalyst as inputs, the warm-up operation amount variable being a variable related to an operation amount of an operation unit of the internal combustion engine, the operation unit of the internal combustion engine being an operation unit used in a warm-up process of the catalyst, and correspondence relation data correlating an integrated value of an intake air amount of the internal combustion engine from a start of the internal combustion engine and the temperature of the catalyst with each other,

the execution device is configured to execute:

the preheating treatment is carried out;

accumulation processing for calculating the accumulation value;

an acquisition process of acquiring a last value of the estimated values of the warm-up operation amount variable and the temperature of the catalyst;

a temperature calculation process of repeatedly calculating an estimated value of the temperature of the catalyst based on an output of the map with the warm-up operation amount variable and the previous value acquired by the acquisition process as inputs to the map;

a determination process of determining that the preheating process is abnormal when a correspondence relationship between the integrated value and the estimated value is different from a correspondence relationship between the integrated value and the temperature of the catalyst in the correspondence relation data; and

and a processing for handling the abnormality by operating predetermined hardware when a determination is made that the abnormality is present.

2. The catalyst warm-up monitoring apparatus for an internal combustion engine according to claim 1,

the internal combustion engine is provided with a valve characteristic varying device configured to vary a valve characteristic of an intake valve,

a variable relating to the valve characteristics, that is, a valve characteristic variable is included in the inputs of the map,

the acquisition process includes a process of acquiring the valve characteristic variable,

the temperature calculation process is a process of calculating the estimated value based on an output of the map in which the input to the map further includes the valve characteristic variable.

3. The catalyst warm-up monitoring apparatus for an internal combustion engine according to claim 1 or 2,

the warm-up operation amount includes a variable related to the ignition timing, that is, an ignition variable.

4. The catalyst warm-up monitoring apparatus for an internal combustion engine according to claim 3,

a variable relating to the injection quantity of the fuel, that is, an injection quantity variable is included in the input of the map,

the acquisition process includes a process of acquiring the injection quantity variable,

the temperature calculation process is a process of calculating the estimated value based on an output of the map in which the input to the map further includes the injection amount variable.

5. The catalyst warm-up monitoring apparatus for an internal combustion engine according to claim 1 or 2,

the warm-up process includes a dither control process of operating a fuel injection valve as the operation portion in order to make a part of cylinders of a plurality of cylinders of the internal combustion engine, in which an air-fuel ratio is richer than a theoretical air-fuel ratio, a cylinder other than the part of cylinders, in a rich combustion cylinder in which the air-fuel ratio is leaner than the theoretical air-fuel ratio, and make a cylinder other than the part of cylinders, in a lean combustion cylinder,

the warm-up operation amount set as an input to the map includes an amplitude value variable that is a variable relating to a degree of richness of the air-fuel ratio of the rich-burn cylinder with respect to a theoretical air-fuel ratio and a degree of leanness of the air-fuel ratio of the lean-burn cylinder with respect to the theoretical air-fuel ratio.

6. The catalyst warm-up monitoring apparatus for an internal combustion engine according to claim 1 or 2,

the internal combustion engine includes a port injection valve that injects fuel into an intake passage and an in-cylinder injection valve that injects fuel into a combustion chamber of the internal combustion engine,

an injection distribution variable that is a variable relating to an injection distribution ratio, which is a ratio of an amount of fuel injected by the port injection valve with respect to a sum of an injection amount of fuel from the port injection valve and an injection amount of fuel from the in-cylinder injection valve, is included in inputs of the map,

the obtaining process includes a process of obtaining the injection distribution variable,

the temperature calculation process is a process of calculating the estimated value based on an output of the map in which an input to the map further includes the injection distribution variable.

7. The catalyst warm-up monitoring apparatus for an internal combustion engine according to claim 1 or 2,

the internal combustion engine is provided with:

an EGR passage configured to allow a fluid flowing into the exhaust passage from a combustion chamber of the internal combustion engine to flow into an intake passage; and

an EGR valve configured to adjust a flow path cross-sectional area of the EGR passage,

an EGR variable that is a variable representing an EGR rate that is a ratio of a flow rate of the fluid flowing into the intake passage via the EGR passage to a sum of the flow rate of the air taken into the intake passage and the flow rate of the fluid flowing into the intake passage via the EGR passage is included in the input of the map,

the acquiring process includes a process of acquiring the EGR variable,

the temperature calculation process is a process of calculating the estimated value based on an output of the map in which an input to the map further includes the EGR variable.

8. The catalyst warm-up monitoring apparatus for an internal combustion engine according to claim 1 or 2,

a variable related to atmospheric pressure that is an atmospheric pressure variable is included in the input of the map,

the obtaining process includes a process of obtaining the atmospheric pressure variable,

the temperature calculation process is a process of calculating the estimated value based on an output of the map in which the input to the map further includes the atmospheric pressure variable.

9. The catalyst warm-up monitoring apparatus for an internal combustion engine according to claim 1 or 2,

the liquid whose flow rate is adjusted by the adjusting device flows to the internal combustion engine,

a variable related to the flow rate of the liquid is included in the input of the map as a flow rate variable,

the acquiring process includes a process of acquiring the flow volume variable,

the temperature calculation process is a process of calculating the estimated value based on an output of the map in which an input to the map further includes the flow rate variable.

10. The catalyst warm-up monitoring apparatus for an internal combustion engine according to claim 1 or 2,

the catalyst is divided into N partial regions arranged in parallel in the flow direction of the fluid flowing into the catalyst, the N partial regions are set as a1 st partial region to an Nth partial region in order from the upstream side of the catalyst,

the acquisition process includes a process of acquiring a previous value of an estimated value of the temperature of each of the 1 st to nth partial regions as a previous value of the estimated value,

the map includes a1 st map and an ith map, the 1 st map being a map for outputting an estimated value of the temperature of the 1 st partial region, the 1 st map having as input at least variables other than an estimated value of the temperature of the partial region located downstream of the 1 st partial region among the variables obtained by the obtaining process, i being an integer of 2 or more and N or less, the ith map being a map for outputting an estimated value of the temperature of the ith partial region, the i-th map having as input at least an estimated value of the temperature of the i-1 th partial region and a previous value of the estimated value of the temperature of the ith partial region,

the temperature calculation process includes a process of calculating an estimated value of the temperature of each of the 1 st to nth partial regions by:

a process of calculating an estimated value of the temperature of the 1 st partial region by inputting to the 1 st map at least variables other than the estimated value of the temperature of the partial region located downstream of the 1 st partial region, among the variables obtained by the obtaining process; and

and a process of calculating an estimated value of the temperature of the i-th partial region by using at least the estimated value of the temperature of the i-th partial region and a last value of the estimated value of the temperature of the i-th partial region as inputs of the i-th map.

11. The catalyst warm-up monitoring apparatus for an internal combustion engine according to claim 1 or 2,

the mapping includes a stability mapping and a time constant mapping,

the stabilization map having the warm-up operation amount variable as an input and outputting a stabilization temperature that is a value at which the temperature of the catalyst converges while the internal combustion engine is operating stably,

the time constant map has an air quantity variable relating to an intake air quantity of the internal combustion engine, the stable temperature, and a last value of the estimated value as inputs, and outputs a time constant variable specifying a time constant for converging a current temperature to the stable temperature,

the acquisition process includes a process of acquiring the air quantity variable,

the temperature calculation process includes:

a steady calculation process of calculating the steady temperature based on an output of the steady map with the preheating operation amount variable as an input;

a time constant calculation process of calculating the time constant variable based on an output of the time constant map with the previous value of the air volume variable, the stable temperature, and the estimated value as an input; and

and a process of calculating an estimated value of the temperature of the catalyst by bringing the estimated value toward the stable temperature based on the time constant variable calculated by the time constant calculation process.

12. The catalyst warm-up monitoring apparatus for an internal combustion engine according to claim 1 or 2,

the coping process includes a notification process for notifying that the preheating process is abnormal by operating a notification device that is the predetermined hardware.

13. A catalyst warm-up monitoring system for an internal combustion engine, comprising the actuator and the storage device according to any one of claims 1 to 12,

the executing device comprises a1 st executing device and a2 nd executing device,

the 1 st execution device is mounted on a vehicle, and configured to execute:

the acquisition process;

a vehicle-side transmission process of transmitting the data acquired by the acquisition process to the outside of the vehicle;

a vehicle-side reception process of receiving a signal based on the estimated value calculated by the temperature calculation process; and

the coping process is carried out by performing a coping process,

the 2 nd actuator is disposed outside the vehicle, and configured to execute:

an external-side reception process of receiving data transmitted by the vehicle-side transmission process;

the temperature calculation process; and

and an external transmission process of transmitting a signal based on the estimated value calculated by the temperature calculation process to the vehicle.

14. A data analysis device is provided, which is capable of analyzing data,

the 2 nd execution device and the storage device according to claim 13 are provided.

15. A control device for an internal combustion engine,

the apparatus according to claim 13 is provided with the 1 st actuator.

16. A kind of receiving device is disclosed, which comprises a receiving unit,

hardware constituting a part of the catalyst warm-up monitoring system according to claim 13, configured to execute the vehicle-side reception process.

17. A catalyst warm-up monitoring method for an internal combustion engine, which is executed by an execution device and a storage device, and which is applied to an internal combustion engine having a catalyst in an exhaust passage, the catalyst warm-up monitoring method comprising:

storing, by the storage device, map data that defines a map in which an estimated value of the temperature of the catalyst is input and output with a previous value of a warm-up operation amount variable that is a variable related to an operation amount of an operation unit of the internal combustion engine that is an operation unit used in a warm-up process of the catalyst and an estimated value of the temperature of the catalyst as inputs, and correspondence relation data that correlates an integrated value of an intake air amount of the internal combustion engine from a start of the internal combustion engine and the temperature of the catalyst with each other;

calculating the accumulated value by the execution device;

obtaining a last value of the estimated values of the warm-up operation amount variable and the temperature of the catalyst;

repeatedly calculating an estimated value of the temperature of the catalyst based on an output of the map with the acquired warm-up operation amount variable and the previous value as inputs to the map;

when the correspondence relationship between the accumulated value and the estimated value is different from the correspondence relationship between the accumulated value and the temperature of the catalyst in the correspondence relation data, a determination is made that the preheating process is abnormal; and

in the case where a determination is made that there is a meaning of the abnormality, the abnormality is dealt with by operating predetermined hardware.